Learning from biological systems how to regularize machine-learning

Abstract

The present disclosure relates to machine-learning generalization, and in particular to techniques for regularizing machine-learning The present disclosure relates to machine-learning generalization, and in particular to techniques for regularizing machine-learning models using biological systems (e.g. brain data) to engineer machine-learning-algorithms that can generalize better. Particularly, aspects are directed to a computer implemented method that includes measuring a plurality of biological responses (e.g. neural responses to stimuli or other variables such body movements); generating data (e.g. responses to stimuli) using the predictive model which can denoise biological data and extract task relevant information; scaling and transforming these predictions (e.g. measure representational similarities between stimuli); and using the biologically derived data to regularize machine-learning-algorithms. The method is applicable in many domains of computer science and artificial intelligence such as perception, learning, memory, cognition, decision making.

1 . A method comprising:
 accessing, by a computing system, a plurality of stimuli for a stimulus scheme;   inputting, by the computing system, a first stimulus of the plurality of stimuli into a neural predictive model;   generating, by the neural predictive model, a prediction of a first neural response of a biological system to the first stimulus;   scaling, by the neural predictive model, the predicted first neural response with a signal-to-noise weight to generate a denoised predicted first neural response; and   providing, by the computing system, the denoised predicted first neural response.   
     
     
         2 . The method of  claim 1 , wherein the signal-to-noise weight (w α )=(signal strength σ 2   α )/(noise strength η 2   α ), where α is a given neuron of the biological system. 
     
     
         3 . The method of  claim 1 , wherein the scaled predicted first neural response is defined as {circumflex over (r)} α1 =w α v α {circumflex over (p)} αi , where (w α )=(signal strength σ 2   α )/(noise strength η 2   α ), α is a given neuron of the biological system and i is the first stimulus, and v α  is a correlation between an actual neural response of the biological system to the first stimulus and the predicted first neural response of the biological system. 
     
     
         4 . The method of  claim 1 , wherein the neural predictive model is a convolutional neural network, the plurality of stimuli are a plurality of images, and the first stimulus is a first image. 
     
     
         5 . The method of  claim 1 , further comprising:
 repeating the inputting of the first stimulus to generate, by the neural predictive model, a plurality of denoised predicted first neural responses for the first stimulus; and   generating, by the neural predictive model, a denoised population first neural response based on the plurality of denoised predicted first neural responses, wherein the denoised population first neural response is a vector of the plurality of denoised predicted first neural responses for the first stimulus.   
     
     
         6 . The method of  claim 5 , further comprising:
 inputting, by the computing system, a second stimulus of the plurality of stimuli into the neural predictive model;   generating, by the neural predictive model, a prediction of a second neural response of the biological system to the second stimulus;   scaling, by the neural predictive model, the predicted second neural response with the signal-to-noise weight to generate a denoised predicted second neural response;   repeating the inputting of the second stimulus to generate, by the neural predictive model, a plurality of denoised predicted second neural responses for the second stimulus; and   generating, by the neural predictive model, a denoised population second neural response based on the plurality of denoised predicted second neural responses, wherein the denoised population second neural response is a vector of plurality of denoised predicted second neural responses for the second stimulus.   
     
     
         7 . The method of  claim 6 , further comprising:
 shifting and normalizing, by the neural predictive model, the denoised population first neural response and the denoised population second neural response to create a centered unit vector for each of the denoised population first neural response and the denoised population second neural response; and   constructing a similarity matrix using the centered unit vector for each of the denoised population first neural response and the denoised population second neural response based on a representation similarity metric.   
     
     
         8 . The method of  claim 6 , wherein the representation similarity metric is S ij   model =ê i ·ê j  for the first image and the second image, where e i =(r i −r)/(∥r i −r∥) where  r =E i [r i ] and e j =(r j −r)/(∥r j −r∥) where  r =E j [r j ]. 
     
     
         9 .- 15 . (canceled) 
     
     
         16 . A method comprising:
 accessing, by a computing system, a plurality of stimuli for a behavioral scheme;   inputting, by the computing system, a first stimulus of the plurality of stimuli into a behavioral predictive model;   generating, by the behavioral predictive model, a prediction of a first behavioral response of a biological system to the first stimulus;   scaling, by the behavioral predictive model, the predicted first behavioral response with a signal-to-noise weight to generate a predicted first behavioral response; and   providing, by the computing system, the predicted first behavioral response.   
     
     
         17 . The method of  claim 16 , wherein the signal-to-noise weight (w α )=(signal strength σ 2   α )/(noise strength η 2   α ), where α is a given behavioral component of the biological system. 
     
     
         18 . The method of  claim 16 , wherein the scaled predicted first behavioral response is defined as {circumflex over (r)} αi =w α v α {circumflex over (p)} αi , where (v α )=(signal strength σ 2   α )/(noise strength η 2   α ), α is a given behavioral component of the biological system and i is the first stimulus, and v α  is a correlation between an actual behavioral response of the biological system to the first stimulus and the predicted first behavioral response of the biological system. 
     
     
         19 . The method of  claim 16 , wherein the behavioral predictive model is a convolutional neural network, the plurality of stimuli are a plurality of stimuli, triggers, and/or behavioral requests, and the first stimulus is a first behavioral request. 
     
     
         20 . The method of  claim 16 , further comprising:
 repeating the inputting of the first stimulus to generate, by the behavior predictive model, a plurality of predicted first behavioral responses for the first stimulus; and   generating, by the behavioral predictive model, a multi-system first behavioral response based on the plurality of predicted first behavioral responses, wherein the multi-system first behavioral response is a vector of the plurality of multi-system predicted first behavioral responses for the first stimulus.   
     
     
         21 . A system comprising:
 one or more processors; and   a memory coupled to the one or more processors, the memory storing a plurality of instructions executable by the one or more processors, the plurality of instructions comprising instructions that when executed by the one or more processors cause the one or more processors to perform the following operations:
 accessing, by a computing system, a plurality of stimuli for a stimulus scheme; 
 inputting, by the computing system, a first stimulus of the plurality of stimuli into a neural predictive model; 
 generating, by the neural predictive model, a prediction of a first neural response of a biological system to the first stimulus; 
 scaling, by the neural predictive model, the predicted first neural response with a signal-to-noise weight to generate a denoised predicted first neural response; and 
 providing, by the computing system, the denoised predicted first neural response. 
   
     
     
         22 . The system of  claim 21 , wherein the signal-to-noise weight (w α )=(signal strength σ 2   α )/(noise strength η 2   α ), where α is a given neuron of the biological system. 
     
     
         23 . The system of  claim 21 , wherein the scaled predicted first neural response is defined as {circumflex over (r)} αi =w α v α {circumflex over (p)} αi , where (w α )=(signal strength σ 2   α )/(noise strength η 2   α ), α is a given neuron of the biological system and i is the first stimulus, and v α  is a correlation between an actual neural response of the biological system to the first stimulus and the predicted first neural response of the biological system. 
     
     
         24 . The system of  claim 21 , wherein the neural predictive model is a convolutional neural network, the plurality of stimuli are a plurality of images, and the first stimulus is a first image. 
     
     
         25 . The system of  claim 21 , wherein the operations further comprise:
 repeating the inputting of the first stimulus to generate, by the neural predictive model, a plurality of denoised predicted first neural responses for the first stimulus; and   generating, by the neural predictive model, a denoised population first neural response based on the plurality of denoised predicted first neural responses, wherein the denoised population first neural response is a vector of the plurality of denoised predicted first neural responses for the first stimulus.   
     
     
         26 . The system of  claim 25 , wherein the operations further comprise:
 inputting, by the computing system, a second stimulus of the plurality of stimuli into the neural predictive model;   generating, by the neural predictive model, a prediction of a second neural response of the biological system to the second stimulus;   scaling, by the neural predictive model, the predicted second neural response with the signal-to-noise weight to generate a denoised predicted second neural response;   repeating the inputting of the second stimulus to generate, by the neural predictive model, a plurality of denoised predicted second neural responses for the second stimulus; and   generating, by the neural predictive model, a denoised population second neural response based on the plurality of denoised predicted second neural responses, wherein the denoised population second neural response is a vector of plurality of denoised predicted second neural responses for the second stimulus.   
     
     
         27 . The system of  claim 26 , wherein the operations further comprise:
 shifting and normalizing, by the neural predictive model, the denoised population first neural response and the denoised population second neural response to create a centered unit vector for each of the denoised population first neural response and the denoised population second neural response; and   constructing a similarity matrix using the centered unit vector for each of the denoised population first neural response and the denoised population second neural response based on a representation similarity metric,   wherein the representation similarity metric is S ij   model =ê i ·ê j  for the first image and the second image, where e i =(r i −r)/(∥r i −r∥) where  r =E i [r i ] and e j =(r j −r)/(∥r j −r∥) where  r =E j [r j ].